**[in bold]**the chapter or section(s) in

*AIMA*that cover each topic.

## Artificial Intelligence

## Natural language processing

Information extraction[Ch. 23, 24][Sec. 23.6]Machine translation[Sec. 23.6, 24.6]Discourse, dialogue and pragmatics[Sec. 23.5]Natural language generation[Sec. 23.6]Speech recognition[Sec. 23.6]Lexical semantics[Sec. 23.4, 24.1]Phonology / morphology[Sec. 23.1]Language resources[Sec. 24.6]## Knowledge representation and reasoning

Description logics[Ch. 10][Sec. 10.5]Semantic networks[Sec. 10.5]Nonmonotonic, default reasoning and belief revision[Sec. 10.6]Probabilistic reasoning[Ch. 13-15]Vagueness and fuzzy logic[Sec. 23.1]Causal reasoning and diagnostics[Sec. 13.5]Temporal reasoning[Ch. 14]Cognitive robotics[Sec. 26.8]Ontology engineering[Sec. 10.1]Logic programming and answer set programming[Sec. 9.4]Spatial and physical reasoning[Sec. 10.6]Reasoning about belief and knowledge[Sec. 10.4]## Planning and scheduling

Planning for deterministic actions[Ch. 11][Sec. 11.1, 11.2]Planning under uncertainty[Sec. 11.5]Multi-agent planning[Ch. 18]Planning with abstraction and generalization[Sec. 11.3, 11.4]Robotic planning[Sec. 26.5]Evolutionary robotics[Sec. 4.1]## Search methodologies

Heuristic function construction[Ch. 3, 4][Sec. 3.5]Discrete space search[Ch. 3]Continuous space search[Sec. 4.2]Randomized search[Sec. 19.8]Game tree search[Ch. 5]Abstraction and micro-operators[Sec. 3.6]Search with partial observations[Sec. 4.4]## Control methods

Robotic planning[Ch. 26][Sec. 26.5]Evolutionary robotics[Sec. 4.1]Computational control theory[Sec. 26.5]Motion path planning[Sec. 26.5]## Philosophical/theoretical foundations of artificial intelligence

Cognitive science[Ch. 27][Sec. 1.1]Theory of mind[Sec. 27.2]## Distributed artificial intelligence

Multi-agent systems[Ch. 18][Ch. 18]Intelligent agents[Ch. 2]Mobile agents[Ch. 26]Cooperation and coordination[Sec. 18.3]## Computer vision

Computer vision tasks[Ch. 25][Sec. 25.7]Image and video acquisition[Sec. 25.3, 25.6]Computer vision representations[Sec. 25.3]Computer vision problems[Sec. 25.7]## Machine learning

Supervised learning[Ch. 19-22][Ch. 19]Ranking[Sec. 18.4]Supervised learning by classification[Sec. 19.6]Supervised learning by regression[Sec. 19.6]Structured outputs[Ch. 19]Cost-sensitive learning[Sec. 22.3]Unsupervised learning[Sec. 20.3]Cluster analysis[Sec. 20.3]Anomaly detection[Sec. 19.9]Mixture modeling[Sec. 20.2]Topic modeling[Ch. 23 Notes]Source separation[N/A] Motif discovery[N/A] Dimensionality reduction and manifold learning[Sec. 21.7]Reinforcement learning[Ch. 22]Sequential decision making[Ch. 17]Inverse reinforcement learning[Sec. 22.6]Apprenticeship learning[Sec. 22.6]Multi-agent reinforcement learning[Sec. 22.7]Adversarial learning[Sec. 21.7]Multi-task learning[Sec. 21.7]Transfer learning[Sec. 21.7]Lifelong machine learning[Ch. 4 Notes]Learning under covariate shift[Sec. 19.9]Learning settings[Sec. 19.8]Batch learning[Sec. 21.4]Online learning settings[Sec. 19.8]Learning from demonstrations[Sec. 22.6]Learning from critiques[Sec. 2.4]Learning from implicit feedback[Sec. 2.4]Active learning settings[Sec. 22.3]Semi-supervised learning settings[Sec. 19.9]Machine learning approaches[Ch. 19]Classification and regression trees[Sec. 19.3]Kernel methods[Sec. 19.7]Support vector machines[Sec. 19.7]Gaussian processes[Sec. 20.3]Neural networks[Ch. 21]Logical and relational learning[Sec. 19.7]Inductive logic learning[Sec. 19.2]Statistical relational learning[Ch. 20]Learning in probabilistic graphical models[Ch. 20]Maximum likelihood modeling[Sec. 20.2]Maximum entropy modeling[Ch. 20]Maximum a posteriori modeling[Sec. 20.1]Mixture models[Sec. 20.3]Latent variable models[Sec. 20.3]Bayesian network models[Ch. 20]Learning linear models[Sec. 19.6]Perceptron algorithm[Ch. 21 Notes]Factorization methods[Sec. 19.9]Non-negative matrix factorization[N/A] Factor analysis[Sec. 19.9]Principal component analysis[Sec. 21.7]Canonical correlation analysis[N/A] Latent Dirichlet allocation[Ch. 23 Notes]Rule learning[Ch. 22 Notes]Instance-based learning[Sec. 19.7]Markov decision processes[Sec. 17.1]Partially-observable Markov decision processes[Sec. 17.4]Stochastic games[Sec. 18.2]Learning latent representations[Sec. 20.3]Deep belief networks[Ch. 21]Bio-inspired approaches[Ch. 4 Notes]Artificial life[Ch. 4 Notes]Evolvable hardware[N/A] Genetic algorithms[Sec. 4.2]Genetic programming[Sec. 4.1]Evolutionary robotics[Sec. 4.1]Generative and developmental approaches[Sec. 20.2]Machine learning algorithms[Ch. 19-22]Dynamic programming for Markov decision processes[Sec. 17.2]Value iteration[Sec. 17.2]Q-learning[Sec. 22.3]Policy iteration[Sec. 17.2]Temporal difference learning[Sec. 22.2]Approximate dynamic programming methods[Sec. 22.2]Ensemble methods[Sec. 19.8]Boosting[Sec. 19.8]Bagging[Sec. 19.8]Spectral methods[N/A] Feature selection[Sec. 19.4]Regularization[Sec. 19.4]Cross-validation[Sec. 19.4]